Lune

CVPR Findings2026

ForgeDreamer: Industrial Text-to-3D Generation with Multi-Expert LoRA and Cross-View Hypergraph

Junhao Cai, Deyu Zeng, Junhao Pang, Lini Li, Xiaopin Zhong, Zongze Wu

Abstract

Current text-to-3D generation methods excel in natural scenes but struggle with industrial applications due to two critical limitations: domain adaptation challenges where conventional LoRA fusion causes knowledge interference across categories, and geometric reasoning deficiencies where pairwise consistency constraints fail to capture higher-order structural dependencies essential for precision manufacturing. We propose a novel framework named ForgeDreamer addressing both challenges through two key innovations. First, we introduce a Multi-Expert LoRA Ensemble mechanism that consolidates multiple category-specific LoRA models into a unified representation, achieving superior crosscategory generalization while eliminating knowledge interference. Second, building on enhanced semantic understanding, we develop a Cross-View Hypergraph Geometric Enhancement approach that captures structural dependencies spanning multiple viewpoints simultaneously. These components work synergistically improved semantic understanding, enables more effective geometric reasoning, while hypergraph modeling ensures manufacturing-level consistency. Extensive experiments on a custom industrial dataset demonstrate superior semantic generalization and enhanced geometric fidelity compared to state-of-the-art approaches. Code is available at https://github.com/Junhaocai27/ ForgeDreamer

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • QLoRA: Efficient Finetuning of Quantized LLMs cites LoRA: Low-Rank Adaptation of Large Language Models
  • 3D Gaussian Splatting for Real-Time Radiance Field Rendering cites Instant neural graphics primitives with a multiresolution hash encoding
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on33

  1. LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
  2. High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
  3. QLoRA: Efficient Finetuning of Quantized LLMsTim Dettmers, Artidoro Pagnoni, Ari Holtzman, Luke ZettlemoyerNeurIPS 2023 · 5,863 citations
  4. 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 5,687 citations
  5. Instant neural graphics primitives with a multiresolution hash encodingThomas Müller, Alex Evans, Christoph Schied, Alexander KellerSIGGRAPH 2022 · 4,089 citations

Related papers

  1. GraphDreamer: Compositional 3D Scene Synthesis from Scene GraphsGege Gao, Weiyang Liu, Anpei Chen, Andreas Geiger et al.CVPR 2024
  2. LEGO-Maker: A Semantic-Driven Algorithm for Text-to-3D GenerationYifei Zhang, Lei ChenICCV 2025 · 1 citation
  3. Pro3D-Editor: A Progressive-Views Perspective for Consistent and Precise 3D EditingYang Zheng, Mengqi Huang, Nan Chen, Zhendong MaoNeurIPS 2025 · 11 citations
  4. Ouroboros3D: Image-to-3D Generation via 3D-aware Recursive DiffusionHao Wen, Zehuan Huang, Yaohui Wang, Xinyuan Chen et al.CVPR 2025
  5. Retrieval-Augmented Score Distillation for Text-to-3D GenerationJunyoung Seo, Susung Hong, Wooseok Jang, Inès Hyeonsu Kim et al.ICML 2024 · 14 citations
Dusk over the sea between two cliffs drawn in fine vertical lines